Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0996. Min Range: -9.0996
Max Act: 9.0996. Min Act: -0.1700
Data Index: 6785454 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.9121. Min Act: -0.1700
Data Index: 7526231 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.8496. Min Act: -0.1700
Data Index: 4517420 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.6621. Min Act: -0.1700
Data Index: 1633525 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.6621. Min Act: -0.1700
Data Index: 4517418 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.6621. Min Act: -0.1700
Data Index: 4720011 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.5371. Min Act: -0.1700
Data Index: 6540491 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.5371. Min Act: -0.1700
Data Index: 448992 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.5371. Min Act: -0.1700
Data Index: 1107397 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.4746. Min Act: -0.1700
Data Index: 3705518 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.4121. Min Act: -0.1700
Data Index: 5466777 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.4121. Min Act: -0.1700
Data Index: 2236059 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.3496. Min Act: -0.1700
Data Index: 8740883 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.3184. Min Act: -0.1700
Data Index: 1257025 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.3184. Min Act: -0.1700
Data Index: 1911054 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.2559. Min Act: -0.1700
Data Index: 4411860 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.2871. Min Act: -0.1700
Data Index: 2947956 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.2559. Min Act: -0.1700
Data Index: 5330786 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.2559. Min Act: -0.1700
Data Index: 2448025 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0996. Min Range: -9.0996
Max Act: 8.2246. Min Act: -0.1700
Data Index: 3731443 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19